{"id":18391,"date":"2018-07-28T18:43:37","date_gmt":"2018-07-28T15:43:37","guid":{"rendered":"https:\/\/hgpu.org\/?p=18391"},"modified":"2018-07-28T18:43:37","modified_gmt":"2018-07-28T15:43:37","slug":"optimization-of-opencl-applications-on-fpga","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=18391","title":{"rendered":"Optimization of OpenCL applications on FPGA"},"content":{"rendered":"<p>Since Moore&#8217;s Law is over, specialized accelerators have becoming more and more trending over the years. FPGA is one of this accelerators and their &quot;reconfigurable hardware&quot; capabilities make it really promising. FPGA are programmed with HDL languages which is hard and time-consuming so many high-level alternatives (such HLS, OpenCL, SystemC, &#8230;) have emerged to provide a better performance\/development time ratio. This document presents a performance and energy comparison between several algorithms on FPGA using OpenCL and we compared with CPU versions using OpenMP and OmpSs. We concluded that FPGA provide better power efficiency than CPU and it can even have better performance in some cases. Our NBody implementation achieve a speedup of 3x over the CPU and 17x in energy consumption.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Since Moore&#8217;s Law is over, specialized accelerators have becoming more and more trending over the years. FPGA is one of this accelerators and their &quot;reconfigurable hardware&quot; capabilities make it really promising. FPGA are programmed with HDL languages which is hard and time-consuming so many high-level alternatives (such HLS, OpenCL, SystemC, &#8230;) have emerged to provide [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,90,3],"tags":[1782,377,1793,298,390],"class_list":["post-18391","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-computer-science","tag-fpga","tag-opencl","tag-optimization","tag-thesis"],"views":2367,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18391","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=18391"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18391\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18391"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18391"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18391"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}